| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9428571428571428, | |
| "eval_steps": 100, | |
| "global_step": 34, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 4.010678382585672, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.3528, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 1.6020709030831801, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0625, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 1.682495021623024, | |
| "learning_rate": 9.412754953531663e-06, | |
| "loss": 0.6977, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.9428571428571428, | |
| "step": 34, | |
| "total_flos": 5795075391488.0, | |
| "train_loss": 0.984823696753558, | |
| "train_runtime": 96.5413, | |
| "train_samples_per_second": 5.759, | |
| "train_steps_per_second": 0.352 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 34, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5795075391488.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |